Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    cracked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nive
    -0.09
    -Level
    -0.09
     Spins
    -0.08
    pus
    -0.08
     niveles
    -0.08
    Levels
    -0.08
     میزان
    -0.08
     مستويات
    -0.08
     mahl
    -0.08
     ό
    -0.08
    POSITIVE LOGITS
     soap
    0.08
     plaster
    0.08
     varn
    0.08
     cookware
    0.07
     constructors
    0.07
    博彩公司
    0.07
     seaside
    0.07
     sidewalks
    0.07
    Svar
    0.07
     SOFTWARE
    0.07
    Act Density 0.003%

    No Known Activations